Скачать или смотреть Robotics Frontiers: Adaptive AI & Sim-to-Real (Nov 18-19, 2025)

Imagine robots that anticipate your needs, learn from videos, and navigate crowds gracefully. This episode of AI Frontiers synthesizes 54 arXiv papers in cs.RO from November 18-19, 2025, exploring robotics' evolution. Key themes include adaptive human-robot collaboration (e.g., robots detecting goal shifts in cooking), advanced motion planning in dynamic environments, learning-based perception and manipulation, safety in specialized applications, sim-to-real transfer, and multimodal AI integration. Standout findings: Scaling data enables robust manipulation; self-supervision boosts efficiency to 99%; topological methods improve navigation by 167%; safety benchmarks enhance VLMs; bio-inspired designs optimize energy; asynchronous models handle long tasks. Methodologies feature RL for adaptation, MPC for real-time control, diffusion policies for robustness, and graph-based approaches for interactions. Deep dives: Ghose et al. on robots adapting to changing human goals via Bayesian inference and planning trees, achieving 40% faster convergence; He et al.'s VIRAL for zero-shot humanoid loco-manipulation via scaled sim-to-real RL; Mattille et al.'s magnetic endoscope for precise fetal surgeries, reducing times by 30%. Future directions: Multimodal fusion, swarm intelligence, ethical frameworks, addressing sim-to-real gaps. Takeaways: Robots as intuitive partners, safe deployment, innovative methods, embodied AI maturity. This synthesis was created using AI tools including GPT Grok using model grok-4-0709 for content generation, TTS synthesis using OpenAI, and image generation using Google.

1. Debasmita Ghose et al. (2025). I've Changed My Mind: Robots Adapting to Changing Human Goals during Collaboration. https://arxiv.org/pdf/2511.15914v1

2. J. Cristobal et al. (2025). Gimballed Rotor Mechanism for Omnidirectional Quadrotors. https://arxiv.org/pdf/2511.15909v1

3. Xiongyi Cai et al. (2025). In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data. https://arxiv.org/pdf/2511.15704v1

4. Sai Puppala et al. (2025). Optimus-Q: Utilizing Federated Learning in Adaptive Robots for Intelligent Nuclear Power Plant Operations through Quantum Cryptography. https://arxiv.org/pdf/2511.15614v1

5. Senyu Fei et al. (2025). SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models. https://arxiv.org/pdf/2511.15605v1

6. Ruoqu Chen et al. (2025). UltraDP: Generalizable Carotid Ultrasound Scanning with Force-Aware Diffusion Policy. https://arxiv.org/pdf/2511.15550v2

7. Chen Cai et al. (2025). NMPC-based Motion Planning with Adaptive Weighting for Dynamic Object Interception. https://arxiv.org/pdf/2511.15532v1

8. Yifei Gao et al. (2025). Decentralized Gaussian Process Classification and an Application in Subsea Robotics. https://arxiv.org/pdf/2511.15529v1

9. Gabriel Lauzier et al. (2025). Theoretical Closed-loop Stability Bounds for Dynamical System Coupled with Diffusion Policies. https://arxiv.org/pdf/2511.15520v1

10. Korbinian Griesbauer et al. (2025). Discovering Optimal Natural Gaits of Dissipative Systems via Virtual Energy Injection. https://arxiv.org/pdf/2511.15513v1

11. Mingyang Feng et al. (2025). RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer. https://arxiv.org/pdf/2511.15414v1

12. Gabriele Calzolari et al. (2025). Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention. https://arxiv.org/pdf/2511.15358v1

13. Nayoung Oh et al. (2025). C2F-Space: Coarse-to-Fine Space Grounding for Spatial Instructions using Vision-Language Models. https://arxiv.org/pdf/2511.15333v1

14. Alexandr Klimchik et al. (2025). MSA - Technique for Stiffness Modeling of Manipulators with Complex and Hybrid Structures. https://arxiv.org/pdf/2511.15294v1

15. Nicolas Gautier et al. (2025). Optimizing Robot Positioning Against Placement Inaccuracies: A Study on the Fanuc CRX10iA/L. https://arxiv.org/pdf/2511.15290v1

16. Jonas De Maeyer et al. (2025). Path Planning through Multi-Agent Reinforcement Learning in Dynamic Environments. https://arxiv.org/pdf/2511.15284v1

17. Jiashu Yang et al. (2025). Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception. https://arxiv.org/pdf/2511.15279v1

18. Alexander Boldachev (2025). Behavior Trees vs Executable Ontologies: a Comparative Analysis of Robot Control Paradigms. https://arxiv.org/pdf/2511.15274v1

19. Tomoki Nakao et al. (2025). Symmetry-Breaking in Multi-Agent Navigation: Winding Number-Aware MPC with a Learned Topological Strategy. https://arxiv.org/pdf/2511.15239v1

20. Hiep Hong Trinh et al. (2025). Modelling and Model-Checking a ROS2 Multi-Robot System using Timed Rebeca. https://arxiv.org/pdf/2511.15227v1

Disclaimer: This video uses arXiv.org content under its API Terms of Use; AI Frontiers is not affiliated with or endorsed by arXiv.org.